Time: 11AM PT/1PM CT/2PM ET
Where: ZOOM.US
Join from PC, Mac, Linux, iOS or Android: https://unl.zoom.us/j/651969661
Or iPhone one-tap :
US: +16699006833,,651969661# or +14086380968,,651969661#
Or Telephone:
Dial(for higher quality, dial a number based on your current location):
US: +1 669 900 6833 or +1 408 638 0968 or +1 646 876 9923
Meeting ID: 651 969 661
International numbers available: https://unl.zoom.us/zoomconference?m=wxCNSgMZiA-cVKSNowGYlQ
Attendees: Ilija, David, Matevz, Marian, BrianB, BrianL, Mat
Excused: Igor, Edgar, JohnH, JohnT, Derek
News/Reminders:
- RUCIO Workshop Feb 28-March 1st in Oslo
- Joint OSG/WLCG/HSP workshop at Thomas Jefferson National Accelerator Facility
https://indico.cern.ch/event/759388/
Early bird is ending tomorrow!
Development:
- xrootd 4.9.0 RC5 out. Discussion about Matevz's critical fixes didn't make it into RC5. Brian points out it's been merged to master before RC5 cut: https://github.com/xrootd/xrootd/commit/442a08438f2f0ec6459698d72d31e6cd2ecfd85a
- will prepare OSG build
- Ilija mentioned he still sees segfaults in RC5
ATLAS:
- Ilija: Slate cluster, and Ilija created cache in Germany, Munich
- BrianL: atlas-xcache from software team provided, Ilija have you tested? Not yet, need hardware. ~1 week get things into slate.
- BrianB: could we have tested containerized atlas-xcache before ATLAS computing week? The work done should be presentable at that time.
CMS:
- Marian: WLCG XRootD Monitoring status - Marian - monitoring for /store CMS path in the collector needed, test new collector with sending cms xrootd data, will setup on red-gridftp13 host at UNL ... set ~1 week to finish the effort included sub-tasks (umbrella ticket STAS-34).
OSG:
- Marian: working on re-registering caches.json used by stashcp into topology, hopefully will submit PR this afternoon
- BrianL: lot of work done in the new packaging as well as in the topology and documentation. Still polishing things up.
- Mat: Wisconsin cache performance still troublesome, same load patterns, not sure it that's normal or not ... BrianB notes they did monitoring stashcp not cvmfs client.
- BrianB: Derek working on proper grafana dashboard for StashCache ... what data are stored at which locations ... Ilija asking about monitoring collector details, where are data being sent? BrianB: on the servers side detailed monitoring being sent to GRACC, summary monitoring is what Derek is working on. Ilija points out monitoring page:
https://gracc.opensciencegrid.org/kibana/app/kibana#/dashboard/AWG5ztK
We want better separation of sent data and distinguish. BrianB agrees, something to do.
- BrianB: mentioned work plan with Software week - document ATLAS and CMS use cases (BrianL), document StashCache (Mat), document carl set of configs for cms and atlas, integration of SciTokens into Cache (Mat); will turn some of this into JIRA tickets
AOB:
- Welcome David Manglano in XCache team, new site representative at UChicago!
- #osg-stashcache slack channel rename to #xcache channel